Abstract
The complexity of the background and the similarities between different types of precision parts, especially in the high-speed movement of conveyor belts in complex industrial scenes, pose immense challenges to the object recognition of precision parts due to diversity in illumination. This study presents a real-time object recognition method for 0.8 cm darning needles and KR22 bearing machine parts under a complex industrial background. First, we propose an image data increase algorithm based on directional flip, and we establish two types of dataset, namely, real data and increased data. We focus on increasing recognition accuracy and reducing computation time, and we design a multilayer feature fusion network to obtain feature information. Subsequently, we propose an accurate method for classifying precision parts on the basis of non-maximal suppression, and then form an improved You Only Look Once (YOLO) V3 network. We implement this method and compare it with models in our real-time industrial object detection experimental platform. Finally, experiments on real and increased datasets show that the proposed method outperforms the YOLO V3 algorithm in terms of recognition accuracy and robustness.
Highlights
Computer vision has been used extensively in the industrial field
Zhang [21] et al used the vibration signals of a deep groove ball bearing, extracted the relevant features, and utilized a neural network to model the degradation for identifying and classifying fault types. These studies focused on algorithmic improvements in convolutional neural networks (CNNs) and innovations in different application scenarios, whereas few studies reported on high-precision parts used in small quantities, especially in the aerospace industry
We proposed an image increase algorithm based on direction reversal (IIA-DR) to expand the data set and verify the feasibility of the IIA-DR
Summary
Computer vision has been used extensively in the industrial field. The use of computer vision in the flexible manufacturing system (FMS) can effectively realize the simultaneous processing of different product parts, and produce flexible and intelligent FMS production management and scheduling [1]. Zhang [21] et al used the vibration signals of a deep groove ball bearing, extracted the relevant features, and utilized a neural network to model the degradation for identifying and classifying fault types These studies focused on algorithmic improvements in CNNs and innovations in different application scenarios, whereas few studies reported on high-precision parts used in small quantities, especially in the aerospace industry. Many difficulties, such as high complexity, low recognition efficiency, and insufficient robustness, still exist in the detection of special mechanical parts with complex illumination and background. We designed an improved neural network structure and feature extraction algorithms based on YOLO V3 for industrial detection platforms, and report refined recognition accuracy.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
